Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder

Abstract Sudden cardiac arrest among young people is a recent worldwide risk, and it is noticed that people with cardiac arrhythmia are more susceptible to various heart diseases. Manual classification can be error-prone, and certainly, there is a need for automation to classify ECG signals to predi...

Full description

Saved in:
Bibliographic Details
Main Authors: Ameet Shah, Dhanpratap Singh, Heba G. Mohamed, Salil Bharany, Ateeq Ur Rehman, Seada Hussen
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-93906-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054401499070464
author Ameet Shah
Dhanpratap Singh
Heba G. Mohamed
Salil Bharany
Ateeq Ur Rehman
Seada Hussen
author_facet Ameet Shah
Dhanpratap Singh
Heba G. Mohamed
Salil Bharany
Ateeq Ur Rehman
Seada Hussen
author_sort Ameet Shah
collection DOAJ
description Abstract Sudden cardiac arrest among young people is a recent worldwide risk, and it is noticed that people with cardiac arrhythmia are more susceptible to various heart diseases. Manual classification can be error-prone, and certainly, there is a need for automation to classify ECG signals to predict cardiac arrhythmia accurately. The proposed self-attention artificial intelligence auto-encoder algorithm proved an effective cardiac arrhythmia classification strategy with a novel modified Kalman filter pre-processing. We achieved 24.00 SNRimp, 0.055 RMSE, 22.1 PRD% for -5db, 20.4 SNRimp, 0.0245 RMSE, 12 PRD% whereas 14.05 SNRimp, 0.010 RMSE, and 7.25 PRD%, which reduces the ECG signal noise during the pre-processing and improves the visibility of the QRS complex and R-R peaks of ECG waveform. The extracted features were used in network of neurons to execute the classification for MIT-BIH arrhythmia databases using the newly developed self-attention autoencoder (AE) algorithm. The results are compared with existing models, revealing that the proposed system outperforms the classification and prediction of cardiac arrhythmia with a precision of 99.91%, recall of 99.86%, and accuracy of 99.71%. It is confirmed that self-attention-AE training results are promising, and it benefits the diagnosis of ECGs for complex cardiac conditions to solve real-world heart problems.
format Article
id doaj-art-bd0214c7e50b45d1aebc1e7a7e66e641
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-bd0214c7e50b45d1aebc1e7a7e66e6412025-08-20T02:52:16ZengNature PortfolioScientific Reports2045-23222025-03-0115112310.1038/s41598-025-93906-5Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoderAmeet Shah0Dhanpratap Singh1Heba G. Mohamed2Salil Bharany3Ateeq Ur Rehman4Seada Hussen5School of Computer Science and Engineering, Lovely Professional UniversitySchool of Computer Science and Engineering, Lovely Professional UniversityDepartment of Electrical Engineering, College of Engineering , Princess Nourah bint Abdulrahman UniversityChitkara University Institute of Engineering and Technology , Chitkara UniversityComputer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical SciencesDepartment of Electrical Power, Adama Science and Technology UniversityAbstract Sudden cardiac arrest among young people is a recent worldwide risk, and it is noticed that people with cardiac arrhythmia are more susceptible to various heart diseases. Manual classification can be error-prone, and certainly, there is a need for automation to classify ECG signals to predict cardiac arrhythmia accurately. The proposed self-attention artificial intelligence auto-encoder algorithm proved an effective cardiac arrhythmia classification strategy with a novel modified Kalman filter pre-processing. We achieved 24.00 SNRimp, 0.055 RMSE, 22.1 PRD% for -5db, 20.4 SNRimp, 0.0245 RMSE, 12 PRD% whereas 14.05 SNRimp, 0.010 RMSE, and 7.25 PRD%, which reduces the ECG signal noise during the pre-processing and improves the visibility of the QRS complex and R-R peaks of ECG waveform. The extracted features were used in network of neurons to execute the classification for MIT-BIH arrhythmia databases using the newly developed self-attention autoencoder (AE) algorithm. The results are compared with existing models, revealing that the proposed system outperforms the classification and prediction of cardiac arrhythmia with a precision of 99.91%, recall of 99.86%, and accuracy of 99.71%. It is confirmed that self-attention-AE training results are promising, and it benefits the diagnosis of ECGs for complex cardiac conditions to solve real-world heart problems.https://doi.org/10.1038/s41598-025-93906-5Cardiac arrhythmiaSelf-attention mechanismAtrial fibrillationDeep learning classificationArtificial intelligencePrediction
spellingShingle Ameet Shah
Dhanpratap Singh
Heba G. Mohamed
Salil Bharany
Ateeq Ur Rehman
Seada Hussen
Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder
Scientific Reports
Cardiac arrhythmia
Self-attention mechanism
Atrial fibrillation
Deep learning classification
Artificial intelligence
Prediction
title Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder
title_full Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder
title_fullStr Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder
title_full_unstemmed Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder
title_short Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder
title_sort electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder
topic Cardiac arrhythmia
Self-attention mechanism
Atrial fibrillation
Deep learning classification
Artificial intelligence
Prediction
url https://doi.org/10.1038/s41598-025-93906-5
work_keys_str_mv AT ameetshah electrocardiogramanalysisforcardiacarrhythmiaclassificationandpredictionthroughselfattentionbasedautoencoder
AT dhanpratapsingh electrocardiogramanalysisforcardiacarrhythmiaclassificationandpredictionthroughselfattentionbasedautoencoder
AT hebagmohamed electrocardiogramanalysisforcardiacarrhythmiaclassificationandpredictionthroughselfattentionbasedautoencoder
AT salilbharany electrocardiogramanalysisforcardiacarrhythmiaclassificationandpredictionthroughselfattentionbasedautoencoder
AT ateequrrehman electrocardiogramanalysisforcardiacarrhythmiaclassificationandpredictionthroughselfattentionbasedautoencoder
AT seadahussen electrocardiogramanalysisforcardiacarrhythmiaclassificationandpredictionthroughselfattentionbasedautoencoder